我使用以下代码在Theano中进行逻辑回归，但一直遇到维度不匹配的错误：
inputs = [[0,0], [1,1], [0,1], [1,0]]outputs = [0, 1, 0, 0]x = T.dmatrix("x")y = T.dvector("y")b = theano.shared(value=1.0, name='b')alpha = 0.01training_steps = 30000w_values = np.asarray(np.random.uniform(low=-1, high=1, size=(2, 1)), dtype=theano.config.floatX)w = theano.shared(value=w_values, name='w', borrow=True)hypothesis = T.nnet.sigmoid(T.dot(x, w) + b)cost = T.sum((y - hypothesis) ** 2)updates = [ (w, w - alpha * T.grad(cost, wrt=w)), (b, b - alpha * T.grad(cost, wrt=b))]train = theano.function(inputs=[x, y], outputs=[hypothesis, cost], updates=updates)test = theano.function(inputs=[x], outputs=[hypothesis])# Trainingcost_history = []for i in range(training_steps): if (i+1) % 5000 == 0: print "Iteration #%s: " % str(i+1) print "Cost: %s" % str(cost) h, cost = train(inputs, outputs) cost_history.append(cost)Theano给出的错误是：
Input dimension mis-match. (input[0].shape[1] = 4, input[1].shape[1] = 1)Apply node that caused the error: Elemwise{sub,no_inplace}(InplaceDimShuffle{x,0}.0, Elemwise{Composite{scalar_sigmoid((i0 + i1))}}[(0, 0)].0)Toposort index: 7Inputs types: [TensorType(float64, row), TensorType(float64, matrix)]Inputs shapes: [(1L, 4L), (4L, 1L)]Inputs strides: [(32L, 8L), (8L, 8L)]Inputs values: [array([[ 0., 1., 0., 0.]]), array([[ 0.73105858], [ 0.70988924], [ 0.68095791], [ 0.75706749]])]所以问题似乎是y被视为1×4，而假设值是4×1，因此无法计算成本
我尝试将输入重塑为4×1，如下所示：
outputs = np.array([0, 1, 0, 0]).reshape(4,1)
这又给我带来了另一个与维度相关的错误：
('Bad input argument to theano function with name "F:/test.py:32" at index 1(0-based)', 'Wrong number of dimensions: expected 1, got 2 with shape (4L, 1L).')
回答：
因为在你的代码中，hypothesis是一个形状为n_sample * 1的矩阵。另一方面，y是一个向量。出现了维度不匹配的情况。你可以扁平化hypothesis或重塑y。以下代码可以工作。
inputs = [[0,0], [1,1], [0,1], [1,0]]outputs = [0, 1, 0, 0]outputs = np.asarray(outputs, dtype='int32').reshape((len(outputs), 1))x = T.dmatrix("x")# y = T.dvector("y")y = T.dmatrix("y")b = theano.shared(value=1.0, name='b')alpha = 0.01training_steps = 30000w_values = np.asarray(np.random.uniform(low=-1, high=1, size=(2, 1)), dtype=theano.config.floatX)w = theano.shared(value=w_values, name='w', borrow=True)hypothesis = T.nnet.sigmoid(T.dot(x, w) + b)# hypothesis = T.flatten(hypothesis)cost = T.sum((y - hypothesis) ** 2)updates = [ (w, w - alpha * T.grad(cost, wrt=w)), (b, b - alpha * T.grad(cost, wrt=b))]train = theano.function(inputs=[x, y], outputs=[hypothesis, cost], updates=updates)test = theano.function(inputs=[x], outputs=[hypothesis])# Trainingcost_history = []for i in range(training_steps): if (i+1) % 5000 == 0: print "Iteration #%s: " % str(i+1) print "Cost: %s" % str(cost) h, cost = train(inputs, outputs) cost_history.append(cost)